Update README.md

README.md

@@ -1,63 +1,8 @@
 # VietCoMath Model Usage
 
 ## Overview
-This repository contains code for running the VietCoMath language model for mathematical problem-solving and text generation tasks.
+This example snipe code for running the VietCoMath-01 small model for mathematical Coding problem-solving and General Multi tasks.
 
-## Installation
-
-### Prerequisites
-- Python 3.8+
-- PyTorch
-- Transformers library
-
-### Required Dependencies
-```bash
-pip install transformers torch
-```
-
-## Usage
-
-### Basic Text Generation
-```python
-import transformers
-import torch
-
-# Load the model
-model_id = "VietnamAIHub/VietCoMath-o1-8B"
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model_id,
-    model_kwargs={"torch_dtype": torch.bfloat16},
-    device_map="auto",
-)
-
-# Prepare messages
-messages = [
-    {"role": "system", "content": ""},
-    {"role": "user", "content": "Who are you?"},
-]
-
-# Define terminators
-terminators = [
-    pipeline.tokenizer.eos_token_id,
-    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
-]
-
-# Generate text
-outputs = pipeline(
-    messages,
-    max_new_tokens=256,
-    eos_token_id=terminators,
-    do_sample=True,
-    temperature=0.6,
-    top_p=0.9,
-)
-
-# Print generated text
-print(outputs[0]["generated_text"][-1])
-```
-
-### Advanced Usage with Response Parsing
 
 #### Helper Functions
 ```python
@@ -116,48 +61,83 @@ def parse_response(response):
         return answer, reflection, steps, ""
 ```
 
-## Example Problem Solving
+
+## Usage
+
+### Basic Text Generation
 ```python
-from openai import OpenAI
+import transformers
+import torch
 
-client = OpenAI(
-    base_url="http://13.65.249.11:8887/v1",
-    api_key="token-abc123",
+# Load the model
+model_id = "VietnamAIHub/VietCoMath-o1-8B"
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device_map="auto",
 )
 
+
 # Example mathematical word problem
+
 problem = "Có 100 sinh viên đỗ đại học. Trong số đó, có 55 sinh viên chọn âm nhạc, 44 sinh viên chọn thể thao, và 20 sinh viên chọn cả 2. Hỏi có bao nhiêu sinh viên không chọn âm nhạc, cũng không chọn thể thao?"
 
-completion = client.chat.completions.create(
-    model="/LLM_32T/pretrained_weights/preview_model/VietCoMath_8B_instruct_2024_11",
-    messages=[
-        {"role": "system", "content": ""},
-        {"role": "user", "content": problem}
-    ],
+# Prepare messages
+messages = [
+    {"role": "system", "content": ""},
+    {"role": "user", "content": f"{problem}"},
+]
+
+# Define terminators
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+# Generate text
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
     temperature=0.6,
     top_p=0.9,
-    max_tokens=4096,
 )
 
-generated_text = completion.choices[0].message.content
+# Print generated text
+generated_text=outputs[0]["generated_text"][-1]
+
 answer, reflection, steps, clarification = parse_response(generated_text)
-```
 
-## Notes
-- Ensure you have a stable internet connection
-- The model requires significant computational resources
-- Performance may vary based on input complexity
+print(clarification)
+print("------------Internal Thinking-------------")
+print(steps)
+print(reflection)
+print("------------End of Internal Thinking-------------\n")
+
+print("------------Final Answer-------------")
+print(answer)
+print("------------End of Answer-------------")
 
 ## Limitations
-- The model is trained primarily on Vietnamese mathematical problems
-- May require fine-tuning for specific use cases
+- The model is Small scale May Failed in Very difficult problems, Please check the result
+
 
 ## License
-[Insert Appropriate License Information]
+[Model is based LLama 3B]
 
 ## Citation
-[If applicable, add citation information for the model]
-```
 
-## Contribution
-Feel free to open issues or submit pull requests to improve the code and documentation.
+@misc {VietnamAIHub,
+	author       = { {VietnamAIHub} },
+	title        = { VietCoMath-o1-8B},
+	year         = 2024,
+	url          = { https://huggingface.co/VietnamAIHub/VietCoMath-o1-8B },
+	doi          = { 10.57967/hf/3743 },
+	publisher    = { Hugging Face }
+}
+
+## Collaboration & Contribution
+Bạn có thể kết nối trực tiếp với Trần Nhiệm [email protected]
+Hoặc có thể chat trực tiếp ở: LinkedIn Facebook. X. Zalo +886 934 311 751